© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70418
    Prev
    Next
    INDEX
    Explanations

    accidents and injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     langsam
    -0.09
     langzaam
    -0.08
     lentamente
    -0.08
     lento
    -0.08
     lungo
    -0.08
    ംഗ
    -0.07
    Obrig
    -0.07
     prova
    -0.07
     remise
    -0.07
     Clube
    -0.07
    POSITIVE LOGITS
     deaths
    0.10
     причин
    0.10
     accidents
    0.09
     fatalities
    0.09
     reasons
    0.08
     contributors
    0.08
     collided
    0.08
     års
    0.08
    өр
    0.08
     injuries
    0.08
    Activations Density 0.016%

    No Known Activations